Research / Selected Projects
Fourier Active Appearance Model
When subjected to unseen and varying illumination conditions, the alignment accuracy of active appearancemodels (AAMs) tends to suffer.In this work we reformulate the problem and propose
a novel framework which can circumvent both these approaches by employing the AAM in the Fourier domain with a bank of filters which can handle substantial illumination variations which is poor in standard AAM and it is much efficient in computationally with a bank of Gabor filters.
Visual-Voice Activity Detection
The detection of voice activity is a challenging problem, especially when the level of acoustic noise is high. Most current approaches only utilise the audio signal, making them susceptible to acoustic noise. An obvious approach to overcome this
is to use the visual modality.
Audio-Visual Automatic Speech Recognition in Vehicles
Acoustically, car cabins are extremely noisy and as a consequence audio-only, in-car voice recognition systems perform poorly. As the visual modality is immune to acoustic noise, using the visual lip information from the driver is seen as a viable strategy in circumventing this problem by using audio visual automatic speech recognition (AVASR).